© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 86764
    Prev
    Next
    INDEX
    Explanations

    port support

    np_acts-logits-general · gemini-2.5-flash-lite

    bioluminescent, voltages, poker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Background
    0.45
    cycled
    0.44
    charge
    0.43
    squeeze
    0.42
     {[
    0.42
    梁
    0.42
    reducing
    0.41
    ranging
    0.41
     показали
    0.41
     पैक
    0.41
    POSITIVE LOGITS
    állítás
    0.53
     vulcan
    0.52
    á
    0.48
    стая
    0.48
    টিউট
    0.47
     plural
    0.47
     albo
    0.46
    ipse
    0.46
    ühm
    0.46
     personally
    0.45
    Activations Density 0.000%

    No Known Activations